MiniMax M2
MiniMax · released Oct 23, 2025
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
Specification
- Context window
- 205K
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 228.7B
- Licence
- other
- Serving providers
- 3
- Moderated
- No
Intelligence
28.9
72th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
119 t/s
Median across providers
Latency
1.17s
Time to first token
Cost per task
$0.09
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)86.8%
- LiveCodeBench82.6%
- MMLU-Pro82.0%
- AIME 202578.3%
- GPQA Diamond77.7%
- IFBench72.3%
- AA-LCR (long context)65.0%
- SciCode36.1%
- Terminal-Bench Hard25.8%
- Humanity's Last Exam13.7%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 86.8% |
| LiveCodeBench | 82.6% |
| MMLU-Pro | 82.0% |
| AIME 2025 | 78.3% |
| GPQA Diamond | 77.7% |
| IFBench | 72.3% |
| AA-LCR (long context) | 65.0% |
| SciCode | 36.1% |
| Terminal-Bench Hard | 25.8% |
| Humanity's Last Exam | 13.7% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Ring-2.6-1TInclusionAI31.1
- o3OpenAI31.1
- Step 3.7 FlashStepFun30.9
- Mistral Medium 3.5Mistral AI30.4
- Qwen3.5-35B-A3BQwen29.9
- Claude Sonnet 4.5Anthropic29.9
- MiniMax M2MiniMax28.9
- Claude Opus 4.1Anthropic28.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Ring-2.6-1T | 31.1 |
| o3 | 31.1 |
| Step 3.7 Flash | 30.9 |
| Mistral Medium 3.5 | 30.4 |
| Qwen3.5-35B-A3B | 29.9 |
| Claude Sonnet 4.5 | 29.9 |
| MiniMax M2 | 28.9 |
| Claude Opus 4.1 | 28.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.255
- Output / 1M tokens
- $1.02
- Cached input / 1M
- Not offered
- Blended 3:1
- $0.446
One task, estimated
$0.09
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).